trigram.py 文件源码

def make_words(text):

    """
    make a list of words from a large bunch of text

    strips all the punctuation and other stuff from a string
    """
    text = strip_punctuation(text)

    # lower-case everything to remove that complication:
    text = text.lower()

    # split into words
    words = text.split()

    # remove the bare single quotes: "'" is both a quote and an apostrophe
    # and capitalize "i"
    words2 = []
    for word in words:
        if word != "'":  # remove quote by itself
            # "i" by itself should be capitalized
            words2.append("I" if word == 'i' else word)
    # could be done with list comprehension too -- next week!
    # words2 = [("I" if word == 'i' else word) for word in words if word != "'"]
    return words2